Merge branch 'from-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git

Patches for 4.16 that are dependent on patches sent to 4.15-rc.

These are small clean ups for the vmw_pvrdma and i40iw drivers.

* 'from-rc' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git:
  RDMA/vmw_pvrdma: Remove usage of BIT() from UAPI header
  RDMA/vmw_pvrdma: Use refcount_t instead of atomic_t
  RDMA/vmw_pvrdma: Use more specific sizeof in kcalloc
  RDMA/vmw_pvrdma: Clarify QP and CQ is_kernel logic
  RDMA/vmw_pvrdma: Add UAR SRQ macros in ABI header file
  i40iw: Change accelerated flag to bool

drivers/infiniband/Kconfig

@@ -1,6 +1,6 @@
 menuconfig INFINIBAND
 	tristate "InfiniBand support"
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAS_DMA
 	depends on NET
 	depends on INET
 	depends on m || IPV6 != m

drivers/infiniband/core/cma.c

@@ -801,6 +801,7 @@ struct rdma_cm_id *rdma_create_id(struct net *net,
 	INIT_LIST_HEAD(&id_priv->mc_list);
 	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
 	id_priv->id.route.addr.dev_addr.net = get_net(net);
+	id_priv->seq_num &= 0x00ffffff;
 
 	return &id_priv->id;
 }
@@ -4453,7 +4454,7 @@ out:
 	return skb->len;
 }
 
-static const struct rdma_nl_cbs cma_cb_table[] = {
+static const struct rdma_nl_cbs cma_cb_table[RDMA_NL_RDMA_CM_NUM_OPS] = {
 	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 

drivers/infiniband/core/device.c

@@ -1136,7 +1136,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[RDMA_NL_LS_NUM_OPS] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
 		.doit = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
@@ -1243,5 +1243,5 @@ static void __exit ib_core_cleanup(void)
 
 MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4);
 
-module_init(ib_core_init);
+subsys_initcall(ib_core_init);
 module_exit(ib_core_cleanup);

drivers/infiniband/core/iwcm.c

@@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason)
 }
 EXPORT_SYMBOL(iwcm_reject_msg);
 
-static struct rdma_nl_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[RDMA_NL_IWPM_NUM_OPS] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},

drivers/infiniband/core/nldev.c

@@ -303,7 +303,7 @@ out:	cb->args[0] = idx;
 	return skb->len;
 }
 
-static const struct rdma_nl_cbs nldev_cb_table[] = {
+static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,

drivers/infiniband/core/security.c

@@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
 	if (ret)
 		return ret;
 
+	if (!qp->qp_sec)
+		return 0;
+
 	mutex_lock(&real_qp->qp_sec->mutex);
 	ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
 					  qp->qp_sec);
@@ -417,8 +420,17 @@ void ib_close_shared_qp_security(struct ib_qp_security *sec)
 
 int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev)
 {
+	u8 i = rdma_start_port(dev);
+	bool is_ib = false;
 	int ret;
 
+	while (i <= rdma_end_port(dev) && !is_ib)
+		is_ib = rdma_protocol_ib(dev, i++);
+
+	/* If this isn't an IB device don't create the security context */
+	if (!is_ib)
+		return 0;
+
 	qp->qp_sec = kzalloc(sizeof(*qp->qp_sec), GFP_KERNEL);
 	if (!qp->qp_sec)
 		return -ENOMEM;
@@ -441,6 +453,10 @@ EXPORT_SYMBOL(ib_create_qp_security);
 
 void ib_destroy_qp_security_begin(struct ib_qp_security *sec)
 {
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	mutex_lock(&sec->mutex);
 
 	/* Remove the QP from the lists so it won't get added to
@@ -470,6 +486,10 @@ void ib_destroy_qp_security_abort(struct ib_qp_security *sec)
 	int ret;
 	int i;
 
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	/* If a concurrent cache update is in progress this
 	 * QP security could be marked for an error state
 	 * transition.  Wait for this to complete.
@@ -505,6 +525,10 @@ void ib_destroy_qp_security_end(struct ib_qp_security *sec)
 {
 	int i;
 
+	/* Return if not IB */
+	if (!sec)
+		return;
+
 	/* If a concurrent cache update is occurring we must
 	 * wait until this QP security structure is processed
 	 * in the QP to error flow before destroying it because
@@ -557,7 +581,7 @@ int ib_security_modify_qp(struct ib_qp *qp,
 {
 	int ret = 0;
 	struct ib_ports_pkeys *tmp_pps;
-	struct ib_ports_pkeys *new_pps;
+	struct ib_ports_pkeys *new_pps = NULL;
 	struct ib_qp *real_qp = qp->real_qp;
 	bool special_qp = (real_qp->qp_type == IB_QPT_SMI ||
 			   real_qp->qp_type == IB_QPT_GSI ||
@@ -565,18 +589,27 @@ int ib_security_modify_qp(struct ib_qp *qp,
 	bool pps_change = ((qp_attr_mask & (IB_QP_PKEY_INDEX | IB_QP_PORT)) ||
 			   (qp_attr_mask & IB_QP_ALT_PATH));
 
+	WARN_ONCE((qp_attr_mask & IB_QP_PORT &&
+		   rdma_protocol_ib(real_qp->device, qp_attr->port_num) &&
+		   !real_qp->qp_sec),
+		   "%s: QP security is not initialized for IB QP: %d\n",
+		   __func__, real_qp->qp_num);
+
 	/* The port/pkey settings are maintained only for the real QP. Open
 	 * handles on the real QP will be in the shared_qp_list. When
 	 * enforcing security on the real QP all the shared QPs will be
 	 * checked as well.
 	 */
 
-	if (pps_change && !special_qp) {
+	if (pps_change && !special_qp && real_qp->qp_sec) {
 		mutex_lock(&real_qp->qp_sec->mutex);
 		new_pps = get_new_pps(real_qp,
 				      qp_attr,
 				      qp_attr_mask);
-
+		if (!new_pps) {
+			mutex_unlock(&real_qp->qp_sec->mutex);
+			return -ENOMEM;
+		}
 		/* Add this QP to the lists for the new port
 		 * and pkey settings before checking for permission
 		 * in case there is a concurrent cache update
@@ -600,7 +633,7 @@ int ib_security_modify_qp(struct ib_qp *qp,
 						 qp_attr_mask,
 						 udata);
 
-	if (pps_change && !special_qp) {
+	if (new_pps) {
 		/* Clean up the lists and free the appropriate
 		 * ports_pkeys structure.
 		 */
@@ -630,6 +663,9 @@ static int ib_security_pkey_access(struct ib_device *dev,
 	u16 pkey;
 	int ret;
 
+	if (!rdma_protocol_ib(dev, port_num))
+		return 0;
+
 	ret = ib_get_cached_pkey(dev, port_num, pkey_index, &pkey);
 	if (ret)
 		return ret;
@@ -663,6 +699,9 @@ int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
 {
 	int ret;
 
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return 0;
+
 	ret = security_ib_alloc_security(&agent->security);
 	if (ret)
 		return ret;
@@ -688,6 +727,9 @@ int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
 
 void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent)
 {
+	if (!rdma_protocol_ib(agent->device, agent->port_num))
+		return;
+
 	security_ib_free_security(agent->security);
 	if (agent->lsm_nb_reg)
 		unregister_lsm_notifier(&agent->lsm_nb);
@@ -695,8 +737,14 @@ void ib_mad_agent_security_cleanup(struct ib_mad_agent *agent)
 
 int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index)
 {
-	if (map->agent.qp->qp_type == IB_QPT_SMI && !map->agent.smp_allowed)
-		return -EACCES;
+	if (!rdma_protocol_ib(map->agent.device, map->agent.port_num))
+		return 0;
+
+	if (map->agent.qp->qp_type == IB_QPT_SMI) {
+		if (!map->agent.smp_allowed)
+			return -EACCES;
+		return 0;
+	}
 
 	return ib_security_pkey_access(map->agent.device,
 				       map->agent.port_num,

drivers/infiniband/core/uverbs_cmd.c

@@ -1968,6 +1968,12 @@ static int modify_qp(struct ib_uverbs_file *file,
 		goto release_qp;
 	}
 
+	if ((cmd->base.attr_mask & IB_QP_ALT_PATH) &&
+	    !rdma_is_port_valid(qp->device, cmd->base.alt_port_num)) {
+		ret = -EINVAL;
+		goto release_qp;
+	}
+
 	attr->qp_state		  = cmd->base.qp_state;
 	attr->cur_qp_state	  = cmd->base.cur_qp_state;
 	attr->path_mtu		  = cmd->base.path_mtu;
@@ -2065,8 +2071,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
 		return -EOPNOTSUPP;
 
 	if (ucore->inlen > sizeof(cmd)) {
-		if (ib_is_udata_cleared(ucore, sizeof(cmd),
-					ucore->inlen - sizeof(cmd)))
+		if (!ib_is_udata_cleared(ucore, sizeof(cmd),
+					 ucore->inlen - sizeof(cmd)))
 			return -EOPNOTSUPP;
 	}
 

drivers/infiniband/core/verbs.c

@@ -1439,7 +1439,8 @@ int ib_close_qp(struct ib_qp *qp)
 	spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);
 
 	atomic_dec(&real_qp->usecnt);
-	ib_close_shared_qp_security(qp->qp_sec);
+	if (qp->qp_sec)
+		ib_close_shared_qp_security(qp->qp_sec);
 	kfree(qp);
 
 	return 0;

drivers/infiniband/hw/cxgb4/cq.c

@@ -395,6 +395,11 @@ next_cqe:
 
 static int cqe_completes_wr(struct t4_cqe *cqe, struct t4_wq *wq)
 {
+	if (DRAIN_CQE(cqe)) {
+		WARN_ONCE(1, "Unexpected DRAIN CQE qp id %u!\n", wq->sq.qid);
+		return 0;
+	}
+
 	if (CQE_OPCODE(cqe) == FW_RI_TERMINATE)
 		return 0;
 
@@ -489,7 +494,7 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 	/*
 	 * Special cqe for drain WR completions...
 	 */
-	if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) {
+	if (DRAIN_CQE(hw_cqe)) {
 		*cookie = CQE_DRAIN_COOKIE(hw_cqe);
 		*cqe = *hw_cqe;
 		goto skip_cqe;
@@ -566,10 +571,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 			ret = -EAGAIN;
 			goto skip_cqe;
 		}
-		if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+		if (unlikely(!CQE_STATUS(hw_cqe) &&
+			     CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
 			t4_set_wq_in_error(wq);
-			hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
-			goto proc_cqe;
+			hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
 		}
 		goto proc_cqe;
 	}
@@ -743,9 +748,6 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 				c4iw_invalidate_mr(qhp->rhp,
 						   CQE_WRID_FR_STAG(&cqe));
 			break;
-		case C4IW_DRAIN_OPCODE:
-			wc->opcode = IB_WC_SEND;
-			break;
 		default:
 			pr_err("Unexpected opcode %d in the CQE received for QPID=0x%0x\n",
 			       CQE_OPCODE(&cqe), CQE_QPID(&cqe));

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -693,8 +693,6 @@ static inline int to_ib_qp_state(int c4iw_qp_state)
 	return IB_QPS_ERR;
 }
 
-#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN
-
 static inline u32 c4iw_ib_to_tpt_access(int a)
 {
 	return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) |

drivers/infiniband/hw/cxgb4/qp.c

@@ -790,21 +790,57 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
 	return 0;
 }
 
-static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
+static int ib_to_fw_opcode(int ib_opcode)
+{
+	int opcode;
+
+	switch (ib_opcode) {
+	case IB_WR_SEND_WITH_INV:
+		opcode = FW_RI_SEND_WITH_INV;
+		break;
+	case IB_WR_SEND:
+		opcode = FW_RI_SEND;
+		break;
+	case IB_WR_RDMA_WRITE:
+		opcode = FW_RI_RDMA_WRITE;
+		break;
+	case IB_WR_RDMA_READ:
+	case IB_WR_RDMA_READ_WITH_INV:
+		opcode = FW_RI_READ_REQ;
+		break;
+	case IB_WR_REG_MR:
+		opcode = FW_RI_FAST_REGISTER;
+		break;
+	case IB_WR_LOCAL_INV:
+		opcode = FW_RI_LOCAL_INV;
+		break;
+	default:
+		opcode = -EINVAL;
+	}
+	return opcode;
+}
+
+static int complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 {
 	struct t4_cqe cqe = {};
 	struct c4iw_cq *schp;
 	unsigned long flag;
 	struct t4_cq *cq;
+	int opcode;
 
 	schp = to_c4iw_cq(qhp->ibqp.send_cq);
 	cq = &schp->cq;
 
+	opcode = ib_to_fw_opcode(wr->opcode);
+	if (opcode < 0)
+		return opcode;
+
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(opcode) |
 				 CQE_TYPE_V(1) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&schp->lock, flag);
@@ -819,6 +855,23 @@ static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
 					   schp->ibcq.cq_context);
 		spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
 	}
+	return 0;
+}
+
+static int complete_sq_drain_wrs(struct c4iw_qp *qhp, struct ib_send_wr *wr,
+				struct ib_send_wr **bad_wr)
+{
+	int ret = 0;
+
+	while (wr) {
+		ret = complete_sq_drain_wr(qhp, wr);
+		if (ret) {
+			*bad_wr = wr;
+			break;
+		}
+		wr = wr->next;
+	}
+	return ret;
 }
 
 static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
@@ -833,9 +886,10 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 
 	cqe.u.drain_cookie = wr->wr_id;
 	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
-				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_OPCODE_V(FW_RI_SEND) |
 				 CQE_TYPE_V(0) |
 				 CQE_SWCQE_V(1) |
+				 CQE_DRAIN_V(1) |
 				 CQE_QPID_V(qhp->wq.sq.qid));
 
 	spin_lock_irqsave(&rchp->lock, flag);
@@ -852,6 +906,14 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
 	}
 }
 
+static void complete_rq_drain_wrs(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
+{
+	while (wr) {
+		complete_rq_drain_wr(qhp, wr);
+		wr = wr->next;
+	}
+}
+
 int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		   struct ib_send_wr **bad_wr)
 {
@@ -868,9 +930,14 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 
 	qhp = to_c4iw_qp(ibqp);
 	spin_lock_irqsave(&qhp->lock, flag);
-	if (t4_wq_in_error(&qhp->wq)) {
+
+	/*
+	 * If the qp has been flushed, then just insert a special
+	 * drain cqe.
+	 */
+	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_sq_drain_wr(qhp, wr);
+		err = complete_sq_drain_wrs(qhp, wr, bad_wr);
 		return err;
 	}
 	num_wrs = t4_sq_avail(&qhp->wq);
@@ -1011,9 +1078,14 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
 	qhp = to_c4iw_qp(ibqp);
 	spin_lock_irqsave(&qhp->lock, flag);
-	if (t4_wq_in_error(&qhp->wq)) {
+
+	/*
+	 * If the qp has been flushed, then just insert a special
+	 * drain cqe.
+	 */
+	if (qhp->wq.flushed) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		complete_rq_drain_wr(qhp, wr);
+		complete_rq_drain_wrs(qhp, wr);
 		return err;
 	}
 	num_wrs = t4_rq_avail(&qhp->wq);
@@ -1285,21 +1357,21 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 	spin_unlock_irqrestore(&rchp->lock, flag);
 
 	if (schp == rchp) {
-		if (t4_clear_cq_armed(&rchp->cq) &&
-		    (rq_flushed || sq_flushed)) {
+		if ((rq_flushed || sq_flushed) &&
+		    t4_clear_cq_armed(&rchp->cq)) {
 			spin_lock_irqsave(&rchp->comp_handler_lock, flag);
 			(*rchp->ibcq.comp_handler)(&rchp->ibcq,
 						   rchp->ibcq.cq_context);
 			spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
 		}
 	} else {
-		if (t4_clear_cq_armed(&rchp->cq) && rq_flushed) {
+		if (rq_flushed && t4_clear_cq_armed(&rchp->cq)) {
 			spin_lock_irqsave(&rchp->comp_handler_lock, flag);
 			(*rchp->ibcq.comp_handler)(&rchp->ibcq,
 						   rchp->ibcq.cq_context);
 			spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
 		}
-		if (t4_clear_cq_armed(&schp->cq) && sq_flushed) {
+		if (sq_flushed && t4_clear_cq_armed(&schp->cq)) {
 			spin_lock_irqsave(&schp->comp_handler_lock, flag);
 			(*schp->ibcq.comp_handler)(&schp->ibcq,
 						   schp->ibcq.cq_context);

drivers/infiniband/hw/cxgb4/t4.h

@@ -197,6 +197,11 @@ struct t4_cqe {
 #define CQE_SWCQE_G(x)    ((((x) >> CQE_SWCQE_S)) & CQE_SWCQE_M)
 #define CQE_SWCQE_V(x)	  ((x)<<CQE_SWCQE_S)
 
+#define CQE_DRAIN_S       10
+#define CQE_DRAIN_M       0x1
+#define CQE_DRAIN_G(x)    ((((x) >> CQE_DRAIN_S)) & CQE_DRAIN_M)
+#define CQE_DRAIN_V(x)	  ((x)<<CQE_DRAIN_S)
+
 #define CQE_STATUS_S      5
 #define CQE_STATUS_M      0x1F
 #define CQE_STATUS_G(x)   ((((x) >> CQE_STATUS_S)) & CQE_STATUS_M)
@@ -213,6 +218,7 @@ struct t4_cqe {
 #define CQE_OPCODE_V(x)   ((x)<<CQE_OPCODE_S)
 
 #define SW_CQE(x)         (CQE_SWCQE_G(be32_to_cpu((x)->header)))
+#define DRAIN_CQE(x)      (CQE_DRAIN_G(be32_to_cpu((x)->header)))
 #define CQE_QPID(x)       (CQE_QPID_G(be32_to_cpu((x)->header)))
 #define CQE_TYPE(x)       (CQE_TYPE_G(be32_to_cpu((x)->header)))
 #define SQ_TYPE(x)	  (CQE_TYPE((x)))

drivers/infiniband/hw/hfi1/hfi.h

@@ -1131,7 +1131,6 @@ struct hfi1_devdata {
 	u16 pcie_lnkctl;
 	u16 pcie_devctl2;
 	u32 pci_msix0;
-	u32 pci_lnkctl3;
 	u32 pci_tph2;
 
 	/*

drivers/infiniband/hw/hfi1/pcie.c

@@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd)
 	if (ret)
 		goto error;
 
-	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
-				     dd->pci_lnkctl3);
-	if (ret)
-		goto error;
-
-	ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
-	if (ret)
-		goto error;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					     dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:
@@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd)
 	if (ret)
 		goto error;
 
-	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
-				    &dd->pci_lnkctl3);
-	if (ret)
-		goto error;
-
-	ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
-	if (ret)
-		goto error;
-
+	if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+		ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+					    &dd->pci_tph2);
+		if (ret)
+			goto error;
+	}
 	return 0;
 
 error:

drivers/infiniband/hw/hfi1/rc.c

@@ -814,7 +814,7 @@ static inline void hfi1_make_rc_ack_16B(struct rvt_qp *qp,
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
 	struct hfi1_16b_header *hdr = &opa_hdr->opah;
 	struct ib_other_headers *ohdr;
-	u32 bth0, bth1;
+	u32 bth0, bth1 = 0;
 	u16 len, pkey;
 	u8 becn = !!is_fecn;
 	u8 l4 = OPA_16B_L4_IB_LOCAL;

drivers/infiniband/hw/hns/hns_roce_alloc.c

@@ -162,14 +162,10 @@ void hns_roce_buf_free(struct hns_roce_dev *hr_dev, u32 size,
 {
 	int i;
 	struct device *dev = hr_dev->dev;
-	u32 bits_per_long = BITS_PER_LONG;
 
 	if (buf->nbufs == 1) {
 		dma_free_coherent(dev, size, buf->direct.buf, buf->direct.map);
 	} else {
-		if (bits_per_long == 64 && buf->page_shift == PAGE_SHIFT)
-			vunmap(buf->direct.buf);
-
 		for (i = 0; i < buf->nbufs; ++i)
 			if (buf->page_list[i].buf)
 				dma_free_coherent(dev, 1 << buf->page_shift,
@@ -185,9 +181,7 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
 {
 	int i = 0;
 	dma_addr_t t;
-	struct page **pages;
 	struct device *dev = hr_dev->dev;
-	u32 bits_per_long = BITS_PER_LONG;
 	u32 page_size = 1 << page_shift;
 	u32 order;
 
@@ -236,23 +230,6 @@ int hns_roce_buf_alloc(struct hns_roce_dev *hr_dev, u32 size, u32 max_direct,
 			buf->page_list[i].map = t;
 			memset(buf->page_list[i].buf, 0, page_size);
 		}
-		if (bits_per_long == 64 && page_shift == PAGE_SHIFT) {
-			pages = kmalloc_array(buf->nbufs, sizeof(*pages),
-					      GFP_KERNEL);
-			if (!pages)
-				goto err_free;
-
-			for (i = 0; i < buf->nbufs; ++i)
-				pages[i] = virt_to_page(buf->page_list[i].buf);
-
-			buf->direct.buf = vmap(pages, buf->nbufs, VM_MAP,
-					       PAGE_KERNEL);
-			kfree(pages);
-			if (!buf->direct.buf)
-				goto err_free;
-		} else {
-			buf->direct.buf = NULL;
-		}
 	}
 
 	return 0;

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -795,11 +795,9 @@ static inline struct hns_roce_qp
 
 static inline void *hns_roce_buf_offset(struct hns_roce_buf *buf, int offset)
 {
-	u32 bits_per_long_val = BITS_PER_LONG;
 	u32 page_size = 1 << buf->page_shift;
 
-	if ((bits_per_long_val == 64 && buf->page_shift == PAGE_SHIFT) ||
-	    buf->nbufs == 1)
+	if (buf->nbufs == 1)
 		return (char *)(buf->direct.buf) + offset;
 	else
 		return (char *)(buf->page_list[offset >> buf->page_shift].buf) +

drivers/infiniband/hw/hns/hns_roce_hem.c

@@ -224,6 +224,7 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
 			sg_init_table(chunk->mem, HNS_ROCE_HEM_CHUNK_LEN);
 			chunk->npages = 0;
 			chunk->nsg = 0;
+			memset(chunk->buf, 0, sizeof(chunk->buf));
 			list_add_tail(&chunk->list, &hem->chunk_list);
 		}
 
@@ -240,8 +241,7 @@ static struct hns_roce_hem *hns_roce_alloc_hem(struct hns_roce_dev *hr_dev,
 		if (!buf)
 			goto fail;
 
-		sg_set_buf(mem, buf, PAGE_SIZE << order);
-		WARN_ON(mem->offset);
+		chunk->buf[chunk->npages] = buf;
 		sg_dma_len(mem) = PAGE_SIZE << order;
 
 		++chunk->npages;
@@ -267,8 +267,8 @@ void hns_roce_free_hem(struct hns_roce_dev *hr_dev, struct hns_roce_hem *hem)
 	list_for_each_entry_safe(chunk, tmp, &hem->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i)
 			dma_free_coherent(hr_dev->dev,
-				   chunk->mem[i].length,
-				   lowmem_page_address(sg_page(&chunk->mem[i])),
+				   sg_dma_len(&chunk->mem[i]),
+				   chunk->buf[i],
 				   sg_dma_address(&chunk->mem[i]));
 		kfree(chunk);
 	}
@@ -722,11 +722,12 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 	struct hns_roce_hem_chunk *chunk;
 	struct hns_roce_hem_mhop mhop;
 	struct hns_roce_hem *hem;
-	struct page *page = NULL;
+	void *addr = NULL;
 	unsigned long mhop_obj = obj;
 	unsigned long obj_per_chunk;
 	unsigned long idx_offset;
 	int offset, dma_offset;
+	int length;
 	int i, j;
 	u32 hem_idx = 0;
 
@@ -763,25 +764,25 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 
 	list_for_each_entry(chunk, &hem->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i) {
+			length = sg_dma_len(&chunk->mem[i]);
 			if (dma_handle && dma_offset >= 0) {
-				if (sg_dma_len(&chunk->mem[i]) >
-				    (u32)dma_offset)
+				if (length > (u32)dma_offset)
 					*dma_handle = sg_dma_address(
 						&chunk->mem[i]) + dma_offset;
-				dma_offset -= sg_dma_len(&chunk->mem[i]);
+				dma_offset -= length;
 			}
 
-			if (chunk->mem[i].length > (u32)offset) {
-				page = sg_page(&chunk->mem[i]);
+			if (length > (u32)offset) {
+				addr = chunk->buf[i] + offset;
 				goto out;
 			}
-			offset -= chunk->mem[i].length;
+			offset -= length;
 		}
 	}
 
 out:
 	mutex_unlock(&table->mutex);
-	return page ? lowmem_page_address(page) + offset : NULL;
+	return addr;
 }
 EXPORT_SYMBOL_GPL(hns_roce_table_find);
 

drivers/infiniband/hw/hns/hns_roce_hem.h

@@ -78,6 +78,7 @@ struct hns_roce_hem_chunk {
 	int			 npages;
 	int			 nsg;
 	struct scatterlist	 mem[HNS_ROCE_HEM_CHUNK_LEN];
+	void			 *buf[HNS_ROCE_HEM_CHUNK_LEN];
 };
 
 struct hns_roce_hem {

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -1131,9 +1131,11 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 {
 	struct hns_roce_v2_mpt_entry *mpt_entry;
 	struct scatterlist *sg;
+	u64 page_addr;
 	u64 *pages;
+	int i, j;
+	int len;
 	int entry;
-	int i;
 
 	mpt_entry = mb_buf;
 	memset(mpt_entry, 0, sizeof(*mpt_entry));
@@ -1191,14 +1193,20 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr,
 
 	i = 0;
 	for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) {
-		pages[i] = ((u64)sg_dma_address(sg)) >> 6;
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		for (j = 0; j < len; ++j) {
+			page_addr = sg_dma_address(sg) +
+				    (j << mr->umem->page_shift);
+			pages[i] = page_addr >> 6;
 
-		/* Record the first 2 entry directly to MTPT table */
-		if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1)
-			break;
-		i++;
+			/* Record the first 2 entry directly to MTPT table */
+			if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1)
+				goto found;
+			i++;
+		}
 	}
 
+found:
 	mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0]));
 	roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M,
 		       V2_MPT_BYTE_56_PA0_H_S,